© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36208
    Prev
    Next
    INDEX
    Explanations

    symbol of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pek
    -0.09
    تصÙģ
    -0.09
    acus
    -0.08
     Ñĥни
    -0.08
    oun
    -0.08
    ä¸ĢäºĽ
    -0.08
     мÑĥ
    -0.08
     gratuitement
    -0.08
    agina
    -0.08
    ahi
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.12
    æĪij对
    0.11
    个人è§ĤçĤ¹
    0.10
    对该
    0.10
    ä¼IJ
    0.10
    éļ¶å±ŀ
    0.10
    ä»Ģä¹ĪæĦıæĢĿ
    0.09
    èµ°åĬ¿
    0.09
    ALAR
    0.09
    éĢģæĿ¥
    0.09
    Activations Density 0.045%

    No Known Activations